Learn More
Ciliary neurotrophic factor (CNTF) acts instructively to switch multipotent stem cells of the CNS to an astrocytic fate. Here we show that CNTF causes activation of janus kinase-signal transducers and activators of transcription and mitogen-activated protein kinase (MAPK) pathways with differential kinetics in these cells. Inhibition studies indicate that(More)
A voice activity detector (VAD) plays a vital role in robust speaker verification, where energy VAD is most commonly used. Energy VAD works well in noise-free conditions but deteriorates in noisy conditions. One way to tackle this is to introduce speech enhancement preprocessing. We study an alternative, likelihood ratio based VAD that trains speech and(More)
Cyclin-dependent kinase 5 (Cdk5) null mice exhibit a unique phenotype characterized by perinatal mortality, disrupted cerebral cortical layering attributable to abnormal neuronal migration, lack of cerebellar foliation, and chromatolytic changes of neurons in the brainstem and the spinal cord. Because Cdk5 is expressed in both neurons and astrocytes, it has(More)
I4U is a joint entry of nine research Institutes and Universities across 4 continents to NIST SRE 2012. It started with a brief discussion during the Odyssey 2012 workshop in Singapore. An online discussion group was soon set up, providing a discussion platform for different issues surrounding NIST SRE'12. Noisy test segments, uneven multi-session training,(More)
The i-vector representation and PLDA classifier have shown state-of-the-art performance for speaker recognition systems. The availability of more than one enrollment utterance for a speaker allows a variety of configurations which can be used to enhance robustness to noise. The well-known technique of multicondition training can be utilized at different(More)
a r t i c l e i n f o a b s t r a c t The availability of multiple utterances (and hence, i-vectors) for speaker enrollment brings up several alternatives for their utilization with probabilistic linear discriminant analysis (PLDA). This paper provides an overview of their effective utilization, from a practical viewpoint. We derive expressions for the(More)
Popular features for speech processing, such as mel-frequency cepstral coefficients (MFCCs), are derived from the short-term magnitude spectrum, whereas the phase spectrum remains unused. While the common argument to use only the magnitude spectrum is that the human ear is phase-deaf, phase-based features have remained less explored due to additional signal(More)
Total variability modeling, based on i-vector extraction of converting a variable-length sequence of feature vectors into a fixed-length i-vector, is currently an adopted parametriza-tion technique for state of-the-art speaker verification systems. However, when the number of the feature vectors is low, uncertainty in the i-vector representation as a point(More)
Human judgment is the final authority in forensic speaker recognition, but the use of modern speaker verification systems with accurate algorithms to perform the task under various circumstances has a huge potential to help the expert. The ultimate goal is to improve the accuracy of automatic systems when challenging data is provided and find a methodology(More)
In this paper, we present a speech activity detection (SAD) technique for speaker verification in noisy environments. The proposed SAD is based on phoneme posteriors derived from a multi-layer perceptron (MLP). The MLP is trained using modulation spectral features, where long temporal segments of the speech signal are analyzed in critical bands. In each(More)